spark-recipe-topic-timeline — Claude Code skill: how to install
Builds a unified chronological narrative of any topic from Spark meeting transcripts and email threads. Useful for catch-ups, onboarding, and status updates.
npx skills add readdle/spark-cli-skills --skill spark-recipe-topic-timeline -a claude-code
npx skills add readdle/spark-cli-skills --skill recipe-topic-timeline -a claude-codeWhat spark-recipe-topic-timeline does
This skill instructs the agent to query Spark CLI for meeting notes and email discussions around a target keyword. If you do not specify a time range, it defaults to 30 days. It inspects meetings via spark meetings and pulls relevant email threads with spark search.
Entries are merged chronologically with date, channel, participants, and a brief summary. The final output includes an executive summary up front, notes on turning points or stalled gaps, and a list of unresolved items at the end.
The recipe requires the use-spark base skill and read-only access to run Spark commands. Without use-spark, the agent cannot parse Spark CLI filter flags.
What it helps with
- reconstruct project history from meeting records and email threads
- prepare an onboarding brief for a new team member
- spot unresolved threads and inactivity gaps in ongoing topics
- compile a chronological status update before a sync
Example prompts for the agent
- Build a topic timeline for project migration over the past 30 days
- Create a chronological summary of billing discussions from Spark emails and meetings
- Catch me up on the redesign topic with key turning points and open items
How to install spark-recipe-topic-timeline
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill spark-recipe-topic-timeline -a claude-codenpx skills add readdle/spark-cli-skills --skill recipe-topic-timeline -a claude-code2Manually: put the files in place
~/.claude/skills/recipe-topic-timeline/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/recipe-topic-timeline/
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-topic-timeline -a codex2Manually: put the files in place
.agents/skills/recipe-topic-timeline/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-topic-timeline -a cursor2Manually: put the files in place
.cursor/skills/recipe-topic-timeline/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install readdle/spark-cli-skills recipe-topic-timeline2Manually: put the files in place
.github/skills/recipe-topic-timeline/SKILL.md1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-topic-timeline -a gemini-cli2Platform CLI
gemini skills install https://github.com/readdle/spark-cli-skills --path skills/recipe-topic-timelineManually: put the files in place
.devin/skills/recipe-topic-timeline/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-topic-timeline -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about spark-recipe-topic-timeline
How do I install spark-recipe-topic-timeline in Claude Code?
Run npx skills add readdle/spark-cli-skills --skill spark-recipe-topic-timeline -a claude-code.
What does spark-recipe-topic-timeline do?
It extracts meeting summaries and email threads via Spark CLI, assembling them into a chronological report with editorial notes.
What prerequisites does this skill require?
It requires the use-spark skill and read-only access permissions to query the Spark CLI tool.
Source text
SKILL.md · MIT
---
name: spark-recipe-topic-timeline
description: >-
Build a chronological narrative for a topic by interleaving meeting transcript
excerpts and email thread summaries across a time range.
metadata:
version: 1.0.0
requires:
skills:
- use-spark
accessLevel: read-only
---
# Recipe: Topic Timeline
For a given project or topic, build a unified chronological narrative by interleaving meeting discussions and email threads. Useful for catching up, briefing someone new, or preparing a status update.
**Prerequisite:** Read the `use-spark` base skill for command reference and filter syntax.
**Access level required:** read-only.
## Steps
### Step 1: Define the scope
Ask the user for:
- The **topic or project name** (keywords to search on)
- The **time range** (default to 30 days if unspecified)
### Step 2: Gather meeting data
```bash
spark meetings --filter "subject:topic-keyword newer_than:30d"
```
If the subject filter misses relevant meetings, broaden:
```bash
spark meetings --filter "newer_than:30d"
```
For each relevant meeting, read the summary:
```bash
spark meeting <id>
```
Pull full detail only for meetings where the topic was a major agenda item:
```bash
spark meeting <id> --transcript --notes
```
Record: date, participants, and the key points related to the topic.
### Step 3: Gather email data
```bash
spark search "topic keyword"
```
For threads that are clearly relevant, read the full conversation:
```bash
spark thread <id>
```
If there are specific people associated with the topic, also pull their threads:
```bash
spark emails --filter "from:[email protected] subject:keyword newer_than:30d"
```
Record: date of each message, participants, and the substance.
### Step 4: Merge into a timeline
Combine all entries (meetings and emails) and sort by date. For each entry:
- **Date**
- **Channel:** Meeting / Email
- **Participants**
- **What happened:** one or two sentences summarizing the key substance
### Step 5: Annotate the timeline
Layer on editorial notes:
- Mark **turning points** where direction changed
- Flag **open threads** that don't have a resolution
- Note **gaps** — periods with no activity that might indicate stalled progress
### Step 6: Present the timeline
Start with a one-paragraph executive summary of where the topic stands now, then present the full timeline oldest-to-newest. End with:
- **Current status:** the latest known state
- **Open items:** anything still unresolved
- **Next touchpoint:** upcoming meeting or pending email that will advance the topic
## Tips
- `spark search` is relevance-ranked and returns full bodies — it's the best starting point for email discovery.
- Meeting summaries usually capture the topic well enough. Reserve `--transcript` for meetings where you need exact quotes or attribution.
- For topics that span many months, work in chunks (e.g., month by month) to avoid overwhelming the output.
- This pairs well with `recipe-decision-tracker` — use that recipe when you only need the decision points, and this one when you need the full narrative.
- If building this for someone else (e.g., onboarding a new team member), call out any assumed context that an outsider wouldn't have.
© readdle · MIT · readdle/spark-cli-skills